http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111583197-A

Outgoing Links

Predicate Object
assignee http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_d6a6f422b091ba12ea61d4adbf1b0e8e
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_c1da3bdc49dbb9ec9048c2d015076d00
classificationCPCAdditional http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30168
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0002
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00
filingDate 2020-04-23-04:00^^<http://www.w3.org/2001/XMLSchema#date>
inventor http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_31cf6eb3073bab12be308e4ce5c8788b
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4ad4bf587b43e9eb95085823f184b2bf
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4c17e2b405adfe1d7c0b0f4b9112cf6f
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ee3b6133ad053041d46ff489cf25f1b5
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_3c809628544bb975d7534fdb043c3cca
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_3ad38790902d3a0f86d88e17c568995f
publicationDate 2020-08-25-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-111583197-A
titleOfInvention Corrosion and damage identification method of power box pictures combined with SSD and Resnet50 network
abstract The invention discloses a method for recognizing corrosion and damage of electric box pictures combined with SSD and Resnet50 network. Collect power box sample pictures, preprocess, screen, sort and label to form a training set; input the training set into the SSD target detection network to predict and output a small picture of the power box, and train to obtain a power box detection model; use the small picture of the power box to input to In the Resnet50 classification network, it is predicted and judged whether the power box is corroded and damaged, and the corrosion and damage detection model is obtained by training; after the test is combined to form a comprehensive model for the identification of corrosion and damage of the power box, and the comprehensive model for the identification of corrosion and damage of the power box is used to realize the picture of the power box to be tested. detection. The present invention can better detect the position of the power box in the image and determine whether there is rust damage and other conditions and results, and solve the problems of large background interference in the photographed image of the power box and difficulty in judging the rust and damage situation.
isCitedBy http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112767364-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113205027-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2022062242-A1
priorityDate 2020-04-23-04:00^^<http://www.w3.org/2001/XMLSchema#date>
type http://data.epo.org/linked-data/def/patent/Publication

Incoming Links

Predicate Subject
isCitedBy http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110675415-A
isDiscussedBy http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID518696
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419527388

Total number of triples: 28.